free-coding-models 0.1.83 → 0.1.85

package/README.md

@@ -72,11 +72,11 @@
 - **🚀 Parallel pings** — All models tested simultaneously via native `fetch`
 - **📊 Real-time animation** — Watch latency appear live in alternate screen buffer
 - **🏆 Smart ranking** — Top 3 fastest models highlighted with medals 🥇🥈🥉
-- **⏱ Continuous monitoring** — Pings all models every 3 seconds forever, never stops
+- **⏱ Adaptive monitoring** — Starts in a fast 2s cadence for 60s, settles to 10s, slows to 30s after 5 minutes idle, and supports a forced 4s mode
 - **📈 Rolling averages** — Avg calculated from ALL successful pings since start
 - **📊 Uptime tracking** — Percentage of successful pings shown in real-time
 - **📐 Stability score** — Composite 0–100 score measuring consistency (p95, jitter, spikes, uptime)
-- **📊 Usage tracking** — Monitor remaining quota percentage for each model directly in the TUI; persists across sessions via `token-stats.json`.
+- **📊 Usage tracking** — Monitor remaining quota for each exact provider/model pair when the provider exposes it; otherwise the TUI shows a green dot instead of a misleading percentage.
 - **📜 Live Log Viewer** — Press `X` to view real-time activity and error logs in a focused TUI overlay.
 - **🛠 MODEL_NOT_FOUND Rotation** — If a specific provider returns a 404 for a model, the TUI intelligently rotates through other available providers for the same model.
 - **🔄 Auto-retry** — Timeout models keep getting retried, nothing is ever "given up on"
@@ -200,7 +200,7 @@ Use `↑↓` arrows to select, `Enter` to confirm. Then the TUI launches with yo
 
 **How it works:**
  1. **Ping phase** — All enabled models are pinged in parallel (up to 150 across 20 providers)
- 2. **Continuous monitoring** — Models are re-pinged every 3 seconds forever
+ 2. **Continuous monitoring** — Models start at 2s re-pings for 60s, then fall back to 10s automatically
 3. **Real-time updates** — Watch "Latest", "Avg", and "Up%" columns update live
 4. **Select anytime** — Use ↑↓ arrows to navigate, press Enter on a model to act
 5. **Smart detection** — Automatically detects if NVIDIA NIM is configured in OpenCode or OpenClaw
@@ -441,17 +441,6 @@ free-coding-models --tier B     # Only B+, B (lightweight options)
 free-coding-models --tier C     # Only C (edge/minimal models)
 ```
 
-#### Dynamic tier filtering with E/D keys
-
-During runtime, use **E** and **D** keys to dynamically adjust the tier filter:
-
-- **E** (Elevate) — Show fewer, higher-tier models (cycle: All → S → A → B → C → All)
-- **D** (Descend) — Show more, lower-tier models (cycle: All → C → B → A → S → All)
-
-Current tier filter is shown in the header badge (e.g., `[Tier S]`)
-
----
-
 ## 📊 TUI Columns
 
 The main table displays one row per model with the following columns:
@@ -463,14 +452,15 @@ The main table displays one row per model with the following columns:
 | **SWE%** | `S` | SWE-bench Verified score — industry-standard for coding |
 | **CTX** | `C` | Context window size (e.g. `128k`) |
 | **Model** | `M` | Model display name (favorites show ⭐ prefix) |
-| **Origin** | `O` | Provider name (NIM, Groq, etc.) — press `N` to cycle origin filter |
+| **Provider** | `O` | Provider name (NIM, Groq, etc.) — press `D` to cycle provider filter |
 | **Latest Ping** | `L` | Most recent round-trip latency in milliseconds |
 | **Avg Ping** | `A` | Rolling average of ALL successful pings since launch |
 | **Health** | `H` | Current status: UP ✅, NO KEY 🔑, Timeout ⏳, Overloaded 🔥, Not Found 🚫 |
 | **Verdict** | `V` | Health verdict based on avg latency + stability analysis |
 | **Stability** | `B` | Composite 0–100 consistency score (see [Stability Score](#-stability-score)) |
 | **Up%** | `U` | Uptime — percentage of successful pings |
-| **Usage** | `G` | Quota remaining — percentage of available tokens/requests left |
+| **Used** | — | Total prompt+completion tokens consumed in logs for this exact provider/model pair, shown in `k` or `M` |
+| **Usage** | `G` | Provider-scoped quota remaining when measurable; otherwise a green dot means usage % is not applicable/reliable for that provider |
 
 ### Verdict values
 
@@ -735,7 +725,7 @@ This script:
 │  1. Enter alternate screen buffer (like vim/htop/less)           │
 │  2. Ping ALL models in parallel                                  │
 │  3. Display real-time table with Latest/Avg/Stability/Up%        │
-│  4. Re-ping ALL models every 3 seconds (forever)               │
+│  4. Re-ping ALL models at 2s on startup, then 10s steady-state │
 │  5. Update rolling averages + stability scores per model        │
 │  6. User can navigate with ↑↓ and select with Enter            │
 │  7. On Enter (OpenCode): set model, launch OpenCode             │
@@ -813,7 +803,7 @@ This script:
 
 **Configuration:**
 - **Ping timeout**: 15 seconds per attempt (slow models get more time)
-- **Ping interval**: 3 seconds between complete re-pings of all models (adjustable with W/X keys)
+- **Ping cadence**: startup burst at 2 seconds for 60s, then 10 seconds normally, 30 seconds when idle for 5 minutes, or forced 4 seconds via `W`
 - **Monitor mode**: Interface stays open forever, press Ctrl+C to exit
 
 **Flags:**
@@ -836,18 +826,17 @@ This script:
 **Keyboard shortcuts (main TUI):**
 - **↑↓** — Navigate models
 - **Enter** — Select model (launches OpenCode or sets OpenClaw default, depending on mode)
-- **R/Y/S/C/M/O/L/A/H/V/B/U/G** — Sort by Rank/Tier/SWE/Ctx/Model/Origin/Latest/Avg/Health/Verdict/Stability/Up%/Usage
+- **R/Y/S/C/M/O/L/A/H/V/B/U/G** — Sort by Rank/Tier/SWE/Ctx/Model/Provider/Latest/Avg/Health/Verdict/Stability/Up%/Usage
 - **F** — Toggle favorite on selected model (⭐ in Model column, pinned at top)
 - **T** — Cycle tier filter (All → S+ → S → A+ → A → A- → B+ → B → C → All)
-- **N** — Cycle origin filter (All → NIM → Groq → ...)
+- **D** — Cycle provider filter (All → NIM → Groq → ...)
 - **Z** — Cycle mode (OpenCode CLI → OpenCode Desktop → OpenClaw)
-- **X** — **Toggle Log Viewer** (view recent activity and error logs)
+- **X** — **Toggle Token Logs** (view recent request/token usage logs)
 - **P** — Open Settings (manage API keys, toggles, updates, profiles)
 - **Shift+P** — Cycle through saved profiles (switches live TUI settings)
 - **Shift+S** — Save current TUI settings as a named profile (inline prompt)
 - **Q** — Open Smart Recommend overlay (find the best model for your task)
-- **E / D** — Elevate / Descend tier filter
-- **W / =** — Decrease / Increase ping interval
+- **W** — Cycle ping mode (`FAST` 2s → `NORMAL` 10s → `SLOW` 30s → `FORCED` 4s)
 - **J / I** — Request feature / Report bug
 - **K / Esc** — Show help overlay / Close overlay
 - **Ctrl+C** — Exit
@@ -873,7 +862,7 @@ Profiles let you save and restore different TUI configurations — useful if you
 - Favorites (starred models)
 - Sort column and direction
 - Tier filter
-- Ping interval
+- Ping mode
 - API keys
 
 **Saving a profile:**